> From: Stefan Kaitschick <stefan.kaitsch...@hamburg.de
> <mailto:stefan.kaitsch...@hamburg.de>>
...
> Last move info is a strange beast, isn't it? I mean, except for ko
> captures, it doesn't really add information to the position. The correct
> prediction rate is such an obvious metric, but maybe prediction shouldn't
> be improved at any price. To a certain degree, last move info is a kind of
> self-delusion. A predictor that does well without it should be a lot more
> robust, even if the percentages are poorer.
My view is that what we really want to compare is temperature in terms of
combinatorial game theory, in other words the urgency of playing locally. In
Go, often the most urgent play remains within the same region for a while. Then
things cool down, and the most urgent play moves elsewhere. So statistically,
most of the urgent moves on the board are local replies.
Lacking a direct measure of temperature/urgency, we use “reply locally when
urgent-looking features exist” as our best cheap approximation.
I have often wondered if a predictor could be trained to just answer this
question “reply locally or not?” One problem of course is that sometimes the
answer depends on the whole rest of the board. But often it does not.
As a concrete experiment, we could define “answer locally” e.g. as “within cfg
distance 4”, and then play the guessing game - how often do professionals and
programs/predictors agree about answering locally? My guess would be quite
often, maybe over 80%. The question is whether it would do any good.
If you look at playout policies, they also struggle with the same issue of
balancing local and nonlocal play in a meaningful way.
Martin_______________________________________________
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
